Head and neck squamous cell carcinoma (HNSCC), the seventh most common cancer worldwide, has become more closely linked to poor lifestyle habits. Despite improvements in cancer treatment approaches, patients with stage I-II HNSCC have a 70-90% 5-year survival rate, and for patients with advanced stages III-IV, this rate falls to about 40%. This controversy is all about the heterogeneity of HNSCC. Finding diagnosis and prognosis biomarkers has the potential to make significant improvements in the life expectancy and overall health of these patients. The combination of bioinformatics and machine learning has facilitated the finding of the best markers for HNSCC. In this regard, RNA expression data were obtained to identify genes that were expressed differently (DEGs) and utilize a deep learning algorithm to identify genes that exhibited significant variability. In addition, correlations between clinical data and DEGs, the building of a Receiver Operating Characteristic (ROC) curve, and the prediction of tumor-infiltrating immune cells were analyzed. Deep learning analysis identified diagnostic and prognostic biomarkers strongly associated with carcinogenesis, such as KRT33B, KRTAP3-3, C14orf34, and ACADM. In addition, after analyzing the ROC curve, it was found that the combination of ACADM, KRT33B, and C14orf34 is the most practical combination of diagnostic markers. This combination achieved sensitivity, specificity, and Area Under the Curve (AUC) values of 0.92, 0.86, and 0.93, respectively.

Department of Computer and Data Sciences Faculty of Mathematical Sciences Shahid Beheshti University Tehran Iran

Department of Health Information Technology and Management School of Allied Sciences Shahid Beheshti University of Medical Sciences Tehran Iran

Department of Laboratory Science School of Allied Medical Science Shahid Beheshti University of Medical Sciences Tehran Iran

Institute of Biophysics and Statistics 1st Faculty of Medicine Charles University Prague Czech Republic

Proteomics Research Center Faculty of Paramedical Sciences Shahid Beheshti University of Medical Sciences Tehran Iran

Proteomics Research Center Shahid Beheshti University of Medical Sciences Tehran Iran

University of Science and Culture Faculty of Science and Advanced Technologies in Biology Tehran Iran

Zobrazit více v PubMed

ACADM Gene - Acyl-CoA Dehydrogenase Medium Chain: GeneCards (The human gene database); (2024) [Available from: https://www.genecards.org/cgi-bin/carddisp.pl?gene=ACADM .

Azari H, Nazari E, Mohit R, Asadnia A, Maftooh M, Nassiri M et al (2023) Machine learning algorithms reveal potential miRNAs biomarkers in gastric cancer. Sci Rep 13(1):6147 PubMed DOI PMC

Cao J, Wu C, Han Z, Liu Z, Yang Z, Ren M, Wang X (2023) Revealing the potential of necroptosis-related genes in prognosis, immune characteristics, and treatment strategies for head and neck squamous cell carcinoma. Sci Rep 13(1):20382 PubMed DOI PMC

Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci 5(7):e623 DOI

Colopi A, Fuda S, Santi S, Onorato A, Cesarini V, Salvati M et al (2023) Impact of age and gender on glioblastoma onset, progression, and management. Mech Ageing Dev 211:111801 PubMed DOI

Cossu AM, Mosca L, Zappavigna S, Misso G, Bocchetti M, De Micco F et al (2019) Long non-coding RNAs as important biomarkers in laryngeal cancer and other head and neck tumours. Int J Mol Sci. https://doi.org/10.3390/ijms20143444 PubMed DOI PMC

Cristina V, Herrera-Gómez RG, Szturz P, Espeli V, Siano M (2019) Immunotherapies and future combination strategies for head and neck squamous cell carcinoma. Int J Mol Sci. https://doi.org/10.3390/ijms20215399 PubMed DOI PMC

Hwang H, Jeon H, Yeo N, Baek D (2024) Big data and deep learning for RNA biology. Exp Mol Med 56(6):1293–1321 PubMed DOI PMC

Jia Z, Li X, Yan Y, Shen X, Wang J, Yang H et al (2022) Exploring the relationship between age and prognosis in glioma: rethinking current age stratification. BMC Neurol 22(1):350 PubMed DOI PMC

Ju G, Yao Z, Zhao Y, Zhao X, Liu F (2023) Data mining on identifying diagnosis and prognosis biomarkers in head and neck squamous carcinoma. Sci Rep 13(1):10020 PubMed DOI PMC

KRT33B Gene - Keratin 33B: GeneCards (THE HUMAN GENE DATABASE) (2024) [updated Jan 3, 2024. Available from: https://www.genecards.org/cgi-bin/carddisp.pl?gene=KRT33B .

KRTAP3–3 Gene - Keratin Associated Protein 3–3: GeneCards (THE HUMAN GENE DATABASE) (2024) [updated Jan 3, 2024. Available from: https://www.genecards.org/cgi-bin/carddisp.pl?gene=KRTAP3-3 .

LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444 PubMed DOI

Li T, Fan J, Wang B, Traugh N, Chen Q, Liu JS et al (2017) TIMER: a web server for comprehensive analysis of tumor-infiltrating immune cells. Cancer Res 77(21):e108–e110 PubMed DOI PMC

Li T, Fu J, Zeng Z, Cohen D, Li J, Chen Q et al (2020a) TIMER2.0 for analysis of tumor-infiltrating immune cells. Nucleic Acids Res 48(W1):W509–W514 PubMed DOI PMC

Li J, Liu X, Nan S, Xu C (2020b) Silencing of long non-coding RNA LINC00520 promotes radiosensitivity of head and neck squamous cell carcinoma cells. Free Radic Res 54(4):254–270 PubMed DOI

Mao X, Cai T, Olyarchuk JG, Wei L (2005) Automated genome annotation and pathway identification using the KEGG Orthology (KO) as a controlled vocabulary. Bioinformatics 21(19):3787–3793 PubMed DOI

Mazzara S, Rossi RL, Grifantini R, Donizetti S, Abrignani S, Bombaci M (2017) CombiROC: an interactive web tool for selecting accurate marker combinations of omics data. Sci Rep 7(1):45477 PubMed DOI PMC

Mody MD, Rocco JW, Yom SS, Haddad RI, Saba NF (2021) Head and neck cancer. Lancet 398(10318):2289–2299 PubMed DOI

Mottaghitalab F, Lanjanian H, Masoudi-Nejad A (2021) Revealing transcriptional and post-transcriptional regulatory mechanisms of γ-glutamyl transferase and keratin isoforms as novel cooperative biomarkers in low-grade glioma and glioblastoma multiforme. Genomics 113(4):2623–2633 PubMed DOI

Nazari E, Pourali G, Khazaei M, Asadnia A, Dashtiahangar M, Mohit R et al (2023) Identification of potential biomarkers in stomach adenocarcinoma using machine learning approaches. Curr Bioinform 18(4):320–333 DOI

Nazari E, Chang H-CH, Deldar K, Pour R, Avan A, Tara M, Mehrabian A (2020) A comprehensive overview of decision fusion technique in healthcare: A systematic scoping review. Iranian Red Crescent Med J 22(10).

Nazari E, Biviji R, Farzin AH, Asgari P, Tabesh H (2021) Advantages and challenges of information fusion technique for big data analysis: proposed framework. J Biostatistics Epidemiol

Nazari E, Biviji R, Roshandel D, Pour R, Shahriari MH, Mehrabian A, Tabesh H (2022) Decision fusion in healthcare and medicine: a narrative review. Mhealth. https://doi.org/10.21037/mhealth-21-15 PubMed DOI PMC

Pandey D, Onkara Perumal P (2023) A scoping review on deep learning for next-generation RNA-Seq. data analysis. Funct Integr Genomics 23(2):134 PubMed DOI

Reimand J, Isserlin R, Voisin V, Kucera M, Tannus-Lopes C, Rostamianfar A, Wadi L, Meyer M, Wong J, Xu C, Merico D (2019) Pathway enrichment analysis and visualization of omics data using g: Profiler, GSEA, Cytoscape and EnrichmentMap. Nat Protoc 14(2):482–517 PubMed DOI PMC

Ru B, Wong CN, Tong Y, Zhong JY, Zhong SSW, Wu WC et al (2019) TISIDB: an integrated repository portal for tumor-immune system interactions. Bioinformatics 35(20):4200–4202 PubMed DOI

Russell M, Aqi A, Saitou M, Gokcumen O, Masuda N (2023) Gene communities in co-expression networks across different tissues. ArXiv

Tan H, Huang H, Yang H, Qian J, Wei L, Liu W (2023) Construction and validation of a prognostic model for tongue cancer based on three genes signature. Medicine (Baltimore) 102(46):e36097 PubMed DOI

Tatachar AV (2021) Comparative assessment of regression models based on model evaluation metrics. Int Res J Eng Technol (IRJET) 8(09):2395–56

Thul PJ, Lindskog C (2018) The human protein atlas: a spatial map of the human proteome. Protein Sci 27(1):233–244 PubMed DOI

Wu Z, You C, Zhu Z, Wu W, Cao J, Xie Q et al (2024) SLA2 is a prognostic marker in HNSCC and correlates with immune cell infiltration in the tumor microenvironment. Eur Arch Otorhinolaryngol 281(1):427–440 PubMed DOI

Xiong Z, Ren S, Chen H, Liu Y, Huang C, Zhang YL et al (2018) PAX9 regulates squamous cell differentiation and carcinogenesis in the oro-oesophageal epithelium. J Pathol 244(2):164–175 PubMed DOI

Xu S, Hu E, Cai Y, Xie Z, Luo X, Zhan L, Tang W, Wang Q, Liu B, Wang R, Xie W (2024) Using clusterProfiler to characterize multiomics data. Nat Protoc 19(11):3292–3320 PubMed DOI

Young A, Whitehouse N, Cho J, Shaw C (2005) OntologyTraverser: an R package for GO analysis. Bioinformatics 21(2):275–276 PubMed DOI

Yu Z, Zhan Y, Guo Y, He D (2023) Better prediction of clinical outcome in clear cell renal cell carcinoma based on a 6 metabolism-related gene signature. Sci Rep 13(1):11490 PubMed DOI PMC

Zafari N, Bathaei P, Velayati M, Khojasteh-Leylakoohi F, Khazaei M, Fiuji H et al (2023) Integrated analysis of multi-omics data for the discovery of biomarkers and therapeutic targets for colorectal cancer. Comput Biol Med 155:106639 PubMed DOI

Zhang Q, Shen J, Wu Y, Ruan W, Zhu F, Duan S (2022) LINC00520: a potential diagnostic and prognostic biomarker in cancer. Front Immunol 13:845418 PubMed DOI PMC

Zou J, Huss M, Abid A, Mohammadi P, Torkamani A, Telenti A (2019) A primer on deep learning in genomics. Nat Genet 51(1):12–18 PubMed DOI